Related papers: A Comparative Study of Training Objectives for Cla…

Fake face detection is a significant challenge for intelligent systems as generative models become more powerful every single day. As the quality of fake faces increases, the trained models become more and more inefficient to detect the…

Clarification need prediction (CNP) is a key task in conversational search, aiming to predict whether to ask a clarifying question or give an answer to the current user query. However, current research on CNP suffers from the issues of…

We propose a novel framework for simultaneously generating and manipulating the face images with desired attributes. While the state-of-the-art attribute editing technique has achieved the impressive performance for creating realistic…

We study permutation invariant training (PIT), which targets at the permutation ambiguity problem for speaker independent source separation models. We extend two state-of-the-art PIT strategies. First, we look at the two-stage speaker…

Foundation models trained on web-scraped datasets propagate societal biases to downstream tasks. While counterfactual generation enables bias analysis, existing methods introduce artifacts by modifying contextual elements like clothing and…

Conditional story generation and contextual text continuation have become increasingly popular topics in NLP community. Existing models are often prone to output paragraphs of texts that gradually diverge from the given prompt. Although the…

Generating and manipulating human facial images using high-level attributal controls are important and interesting problems. The models proposed in previous work can solve one of these two problems (generation or manipulation), but not both…

In light of the success of the pre-trained language models (PLMs), continual pre-training of generic PLMs has been the paradigm of domain adaption. In this paper, we propose QUERT, A Continual Pre-trained Language Model for QUERy…

In this paper, we address the problem of conditional modality learning, whereby one is interested in generating one modality given the other. While it is straightforward to learn a joint distribution over multiple modalities using a deep…

Existing multimodal generative models fall short as qualified design copilots, as they often struggle to generate imaginative outputs once instructions are less detailed or lack the ability to maintain consistency with the provided…

Personalized image generation via text prompts has great potential to improve daily life and professional work by facilitating the creation of customized visual content. The aim of image personalization is to create images based on a…

Curriculum learning allows complex tasks to be mastered via incremental progression over `stepping stone' goals towards a final desired behaviour. Typical implementations learn locomotion policies for challenging environments through…

Users often need to look through multiple search result pages or reformulate queries when they have complex information-seeking needs. Conversational search systems make it possible to improve user satisfaction by asking questions to…

Visual counterfactual explanations identify modifications to an image that would change the prediction of a classifier. We propose a set of techniques based on generative models (VAE) and a classifier ensemble directly trained in the latent…

Conversational query clarification enables users to refine their search queries through interactive dialogue, improving search effectiveness. Traditional approaches rely on text-based clarifying questions, which often fail to capture…

Providing a human-understandable explanation of classifiers' decisions has become imperative to generate trust in their use for day-to-day tasks. Although many works have addressed this problem by generating visual explanation maps, they…

Ability to generate intelligent and generalizable facial expressions is essential for building human-like social robots. At present, progress in this field is hindered by the fact that each facial expression needs to be programmed by…

We introduce a novel framework named ClarifyGPT, which aims to enhance code generation by empowering LLMs with the ability to identify ambiguous requirements and ask targeted clarifying questions. In particular, ClarifyGPT first detects…

Saliency methods have been widely used to highlight important input features in model predictions. Most existing methods use backpropagation on a modified gradient function to generate saliency maps. Thus, noisy gradients can result in…

While fine-tuning is the standard for injecting factual knowledge into large language models (LLMs), the mechanisms enabling reliable fact recall via unseen queries remain poorly understood. Common two-stage training strategies, which…